blob: 00d5c0afcc6a1486cb259214431c4a958606cbf2 [file] [log] [blame]
// Copyright 2018 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
#include "go_asm.h"
#include "textflag.h"
TEXT ·Equal(SB),NOSPLIT,$0-25
MOVL a_len+4(FP), BX
MOVL b_len+16(FP), CX
CMPL BX, CX
JNE neq
MOVL a_base+0(FP), SI
MOVL b_base+12(FP), DI
CMPL SI, DI
JEQ eq
CALL memeqbody<>(SB)
MOVB AX, ret+24(FP)
RET
neq:
MOVB $0, ret+24(FP)
RET
eq:
MOVB $1, ret+24(FP)
RET
// memequal(a, b unsafe.Pointer, size uintptr) bool
TEXT runtime·memequal(SB),NOSPLIT,$0-17
MOVL a+0(FP), SI
MOVL b+4(FP), DI
CMPL SI, DI
JEQ eq
MOVL size+8(FP), BX
CALL memeqbody<>(SB)
MOVB AX, ret+16(FP)
RET
eq:
MOVB $1, ret+16(FP)
RET
// memequal_varlen(a, b unsafe.Pointer) bool
TEXT runtime·memequal_varlen(SB),NOSPLIT,$0-9
MOVL a+0(FP), SI
MOVL b+4(FP), DI
CMPL SI, DI
JEQ eq
MOVL 4(DX), BX // compiler stores size at offset 4 in the closure
CALL memeqbody<>(SB)
MOVB AX, ret+8(FP)
RET
eq:
MOVB $1, ret+8(FP)
RET
// a in SI
// b in DI
// count in BX
TEXT memeqbody<>(SB),NOSPLIT,$0-0
XORQ AX, AX
CMPQ BX, $8
JB small
// 64 bytes at a time using xmm registers
hugeloop:
CMPQ BX, $64
JB bigloop
MOVOU (SI), X0
MOVOU (DI), X1
MOVOU 16(SI), X2
MOVOU 16(DI), X3
MOVOU 32(SI), X4
MOVOU 32(DI), X5
MOVOU 48(SI), X6
MOVOU 48(DI), X7
PCMPEQB X1, X0
PCMPEQB X3, X2
PCMPEQB X5, X4
PCMPEQB X7, X6
PAND X2, X0
PAND X6, X4
PAND X4, X0
PMOVMSKB X0, DX
ADDQ $64, SI
ADDQ $64, DI
SUBQ $64, BX
CMPL DX, $0xffff
JEQ hugeloop
RET
// 8 bytes at a time using 64-bit register
bigloop:
CMPQ BX, $8
JBE leftover
MOVQ (SI), CX
MOVQ (DI), DX
ADDQ $8, SI
ADDQ $8, DI
SUBQ $8, BX
CMPQ CX, DX
JEQ bigloop
RET
// remaining 0-8 bytes
leftover:
ADDQ BX, SI
ADDQ BX, DI
MOVQ -8(SI), CX
MOVQ -8(DI), DX
CMPQ CX, DX
SETEQ AX
RET
small:
CMPQ BX, $0
JEQ equal
LEAQ 0(BX*8), CX
NEGQ CX
CMPB SI, $0xf8
JA si_high
// load at SI won't cross a page boundary.
MOVQ (SI), SI
JMP si_finish
si_high:
// address ends in 11111xxx. Load up to bytes we want, move to correct position.
MOVQ BX, DX
ADDQ SI, DX
MOVQ -8(DX), SI
SHRQ CX, SI
si_finish:
// same for DI.
CMPB DI, $0xf8
JA di_high
MOVQ (DI), DI
JMP di_finish
di_high:
MOVQ BX, DX
ADDQ DI, DX
MOVQ -8(DX), DI
SHRQ CX, DI
di_finish:
SUBQ SI, DI
SHLQ CX, DI
equal:
SETEQ AX
RET